Presentation	2011/12/12 Automatic Transcription of Lecture Speech using Language Model based on Speaking-Style Transformation of Proceeding Texts MAKOTO WATANABE, YUYA AKITA, TATSUYA KAWAHARA,
PDF Download Page	PDF download Page Link
Abstract(in Japanese)	(See Japanese page)
Abstract(in English)	For automatic speech recognition of spontaneous lecture speech, language models need to cover spoken-style expressions such as fillers and colloquial expressions, as well as domain-dependent topic words. We propose an approach to make a spoken-style language model from written-style texts by combining two transformation methods: a rule-based text transformation using lexical and syntactic information, and statistical transformation of N-gram entries. Experiments over academic presentations were conducted to evaluate the proposed approach.
Keyword(in Japanese)	(See Japanese page)
Keyword(in English)
Paper #	Vol.2011-SLP-89 No.1
Date of Issue

Conference Information
Committee	NLC
Conference Date	2011/12/12(1days)
Place (in Japanese)	(See Japanese page)
Place (in English)
Topics (in Japanese)	(See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To	Natural Language Understanding and Models of Communication (NLC)
Language	JPN
Title (in Japanese)	(See Japanese page)
Sub Title (in Japanese)	(See Japanese page)
Title (in English)	Automatic Transcription of Lecture Speech using Language Model based on Speaking-Style Transformation of Proceeding Texts
Sub Title (in English)
Keyword(1)
1st Author's Name	MAKOTO WATANABE
1st Author's Affiliation	Graduate School of Informatics, Kyoto University()
2nd Author's Name	YUYA AKITA
2nd Author's Affiliation	Graduate School of Informatics, Kyoto University
3rd Author's Name	TATSUYA KAWAHARA
3rd Author's Affiliation	Graduate School of Informatics, Kyoto University
Date	2011/12/12
Paper #	Vol.2011-SLP-89 No.1
Volume (vol)	vol.111
Number (no)	364
Page	pp.pp.-
#Pages	6
Date of Issue